In [1]:
# !pip install git+https://github.com/alberanid/imdbpy
# !pip install pandas
# !pip install numpy
# !pip install matplotlib
# !pip install seaborn
# !pip install pandas_profiling --upgrade
# !pip install plotly
# !pip install wordcloud
# !pip install Flask
In [2]:
# Import Dataset
# Import File from Loacal Drive
# from google.colab import files
# data_to_load = files.upload()
# from google.colab import drive
# drive.mount('/content/drive')
In [3]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
import collections
import plotly.express as px
import plotly.graph_objects as go
import nltk
import re
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.probability import FreqDist
from nltk.util import ngrams
from plotly.subplots import make_subplots
from plotly.offline import iplot, init_notebook_mode
from wordcloud import WordCloud, STOPWORDS
from pandas_profiling import ProfileReport
%matplotlib inline
warnings.filterwarnings("ignore")
In [4]:
nltk.download('all')
[nltk_data] Downloading collection 'all'
[nltk_data]    | 
[nltk_data]    | Downloading package abc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package abc is already up-to-date!
[nltk_data]    | Downloading package alpino to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package alpino is already up-to-date!
[nltk_data]    | Downloading package biocreative_ppi to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package biocreative_ppi is already up-to-date!
[nltk_data]    | Downloading package brown to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package brown is already up-to-date!
[nltk_data]    | Downloading package brown_tei to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package brown_tei is already up-to-date!
[nltk_data]    | Downloading package cess_cat to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cess_cat is already up-to-date!
[nltk_data]    | Downloading package cess_esp to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cess_esp is already up-to-date!
[nltk_data]    | Downloading package chat80 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package chat80 is already up-to-date!
[nltk_data]    | Downloading package city_database to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package city_database is already up-to-date!
[nltk_data]    | Downloading package cmudict to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cmudict is already up-to-date!
[nltk_data]    | Downloading package comparative_sentences to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package comparative_sentences is already up-to-
[nltk_data]    |       date!
[nltk_data]    | Downloading package comtrans to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package comtrans is already up-to-date!
[nltk_data]    | Downloading package conll2000 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2000 is already up-to-date!
[nltk_data]    | Downloading package conll2002 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2002 is already up-to-date!
[nltk_data]    | Downloading package conll2007 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2007 is already up-to-date!
[nltk_data]    | Downloading package crubadan to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package crubadan is already up-to-date!
[nltk_data]    | Downloading package dependency_treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package dependency_treebank is already up-to-date!
[nltk_data]    | Downloading package dolch to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package dolch is already up-to-date!
[nltk_data]    | Downloading package europarl_raw to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package europarl_raw is already up-to-date!
[nltk_data]    | Downloading package floresta to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package floresta is already up-to-date!
[nltk_data]    | Downloading package framenet_v15 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package framenet_v15 is already up-to-date!
[nltk_data]    | Downloading package framenet_v17 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package framenet_v17 is already up-to-date!
[nltk_data]    | Downloading package gazetteers to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package gazetteers is already up-to-date!
[nltk_data]    | Downloading package genesis to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package genesis is already up-to-date!
[nltk_data]    | Downloading package gutenberg to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package gutenberg is already up-to-date!
[nltk_data]    | Downloading package ieer to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ieer is already up-to-date!
[nltk_data]    | Downloading package inaugural to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package inaugural is already up-to-date!
[nltk_data]    | Downloading package indian to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package indian is already up-to-date!
[nltk_data]    | Downloading package jeita to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package jeita is already up-to-date!
[nltk_data]    | Downloading package kimmo to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package kimmo is already up-to-date!
[nltk_data]    | Downloading package knbc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package knbc is already up-to-date!
[nltk_data]    | Downloading package lin_thesaurus to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package lin_thesaurus is already up-to-date!
[nltk_data]    | Downloading package mac_morpho to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mac_morpho is already up-to-date!
[nltk_data]    | Downloading package machado to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package machado is already up-to-date!
[nltk_data]    | Downloading package masc_tagged to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package masc_tagged is already up-to-date!
[nltk_data]    | Downloading package moses_sample to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package moses_sample is already up-to-date!
[nltk_data]    | Downloading package movie_reviews to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package movie_reviews is already up-to-date!
[nltk_data]    | Downloading package names to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package names is already up-to-date!
[nltk_data]    | Downloading package nombank.1.0 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nombank.1.0 is already up-to-date!
[nltk_data]    | Downloading package nps_chat to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nps_chat is already up-to-date!
[nltk_data]    | Downloading package omw to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package omw is already up-to-date!
[nltk_data]    | Downloading package opinion_lexicon to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package opinion_lexicon is already up-to-date!
[nltk_data]    | Downloading package paradigms to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package paradigms is already up-to-date!
[nltk_data]    | Downloading package pil to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pil is already up-to-date!
[nltk_data]    | Downloading package pl196x to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pl196x is already up-to-date!
[nltk_data]    | Downloading package ppattach to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ppattach is already up-to-date!
[nltk_data]    | Downloading package problem_reports to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package problem_reports is already up-to-date!
[nltk_data]    | Downloading package propbank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package propbank is already up-to-date!
[nltk_data]    | Downloading package ptb to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ptb is already up-to-date!
[nltk_data]    | Downloading package product_reviews_1 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package product_reviews_1 is already up-to-date!
[nltk_data]    | Downloading package product_reviews_2 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package product_reviews_2 is already up-to-date!
[nltk_data]    | Downloading package pros_cons to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pros_cons is already up-to-date!
[nltk_data]    | Downloading package qc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package qc is already up-to-date!
[nltk_data]    | Downloading package reuters to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package reuters is already up-to-date!
[nltk_data]    | Downloading package rte to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package rte is already up-to-date!
[nltk_data]    | Downloading package semcor to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package semcor is already up-to-date!
[nltk_data]    | Downloading package senseval to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package senseval is already up-to-date!
[nltk_data]    | Downloading package sentiwordnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sentiwordnet is already up-to-date!
[nltk_data]    | Downloading package sentence_polarity to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sentence_polarity is already up-to-date!
[nltk_data]    | Downloading package shakespeare to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package shakespeare is already up-to-date!
[nltk_data]    | Downloading package sinica_treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sinica_treebank is already up-to-date!
[nltk_data]    | Downloading package smultron to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package smultron is already up-to-date!
[nltk_data]    | Downloading package state_union to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package state_union is already up-to-date!
[nltk_data]    | Downloading package stopwords to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package stopwords is already up-to-date!
[nltk_data]    | Downloading package subjectivity to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package subjectivity is already up-to-date!
[nltk_data]    | Downloading package swadesh to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package swadesh is already up-to-date!
[nltk_data]    | Downloading package switchboard to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package switchboard is already up-to-date!
[nltk_data]    | Downloading package timit to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package timit is already up-to-date!
[nltk_data]    | Downloading package toolbox to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package toolbox is already up-to-date!
[nltk_data]    | Downloading package treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package treebank is already up-to-date!
[nltk_data]    | Downloading package twitter_samples to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package twitter_samples is already up-to-date!
[nltk_data]    | Downloading package udhr to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package udhr is already up-to-date!
[nltk_data]    | Downloading package udhr2 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package udhr2 is already up-to-date!
[nltk_data]    | Downloading package unicode_samples to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package unicode_samples is already up-to-date!
[nltk_data]    | Downloading package universal_treebanks_v20 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package universal_treebanks_v20 is already up-to-
[nltk_data]    |       date!
[nltk_data]    | Downloading package verbnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package verbnet is already up-to-date!
[nltk_data]    | Downloading package verbnet3 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package verbnet3 is already up-to-date!
[nltk_data]    | Downloading package webtext to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package webtext is already up-to-date!
[nltk_data]    | Downloading package wordnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wordnet is already up-to-date!
[nltk_data]    | Downloading package wordnet_ic to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wordnet_ic is already up-to-date!
[nltk_data]    | Downloading package words to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package words is already up-to-date!
[nltk_data]    | Downloading package ycoe to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ycoe is already up-to-date!
[nltk_data]    | Downloading package rslp to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package rslp is already up-to-date!
[nltk_data]    | Downloading package maxent_treebank_pos_tagger to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package maxent_treebank_pos_tagger is already up-
[nltk_data]    |       to-date!
[nltk_data]    | Downloading package universal_tagset to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package universal_tagset is already up-to-date!
[nltk_data]    | Downloading package maxent_ne_chunker to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package maxent_ne_chunker is already up-to-date!
[nltk_data]    | Downloading package punkt to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package punkt is already up-to-date!
[nltk_data]    | Downloading package book_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package book_grammars is already up-to-date!
[nltk_data]    | Downloading package sample_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sample_grammars is already up-to-date!
[nltk_data]    | Downloading package spanish_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package spanish_grammars is already up-to-date!
[nltk_data]    | Downloading package basque_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package basque_grammars is already up-to-date!
[nltk_data]    | Downloading package large_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package large_grammars is already up-to-date!
[nltk_data]    | Downloading package tagsets to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package tagsets is already up-to-date!
[nltk_data]    | Downloading package snowball_data to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package snowball_data is already up-to-date!
[nltk_data]    | Downloading package bllip_wsj_no_aux to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package bllip_wsj_no_aux is already up-to-date!
[nltk_data]    | Downloading package word2vec_sample to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package word2vec_sample is already up-to-date!
[nltk_data]    | Downloading package panlex_swadesh to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package panlex_swadesh is already up-to-date!
[nltk_data]    | Downloading package mte_teip5 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mte_teip5 is already up-to-date!
[nltk_data]    | Downloading package averaged_perceptron_tagger to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package averaged_perceptron_tagger is already up-
[nltk_data]    |       to-date!
[nltk_data]    | Downloading package averaged_perceptron_tagger_ru to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package averaged_perceptron_tagger_ru is already
[nltk_data]    |       up-to-date!
[nltk_data]    | Downloading package perluniprops to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package perluniprops is already up-to-date!
[nltk_data]    | Downloading package nonbreaking_prefixes to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nonbreaking_prefixes is already up-to-date!
[nltk_data]    | Downloading package vader_lexicon to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package vader_lexicon is already up-to-date!
[nltk_data]    | Downloading package porter_test to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package porter_test is already up-to-date!
[nltk_data]    | Downloading package wmt15_eval to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wmt15_eval is already up-to-date!
[nltk_data]    | Downloading package mwa_ppdb to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mwa_ppdb is already up-to-date!
[nltk_data]    | 
[nltk_data]  Done downloading collection all
Out[4]:
True
In [5]:
# path = '/content/drive/MyDrive/Files/'

path = 'C:\\Users\\pawan\\OneDrive\\Desktop\\ott\\Data\\'
 
df_tvshows = pd.read_csv(path + 'otttvshows.csv')
 
df_tvshows.head()
Out[5]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country Language Plotline Runtime Kind Seasons Netflix Hulu Prime Video Disney+ Type
0 1 Snowpiercer 2013 18+ 6.9 94% NaN Daveed Diggs,Iddo Goldberg,Mickey Sumner,Aliso... Action,Drama,Sci-Fi,Thriller United States English Set seven years after the world has become a f... 60.0 tv series 3.0 1 0 0 0 1
1 2 Philadelphia 1993 13+ 8.8 80% NaN Charlie Day,Glenn Howerton,Rob McElhenney,Kait... Comedy United States English The gang, 5 raging alcoholic, narcissists run ... 22.0 tv series 18.0 1 0 0 0 1
2 3 Roma 2018 18+ 8.7 93% NaN Kevin McKidd,Ray Stevenson,Polly Walker,Kerry ... Action,Drama,History,Romance,War United Kingdom,United States English In this British historical drama, the turbulen... 52.0 tv series 2.0 1 0 0 0 1
3 4 Amy 2015 18+ 7.0 87% NaN Amy Brenneman,Richard T. Jones,Jessica Tuck,Ma... Drama United States English A family drama focused on three generations of... 60.0 tv series 6.0 1 0 1 1 1
4 5 The Young Offenders 2016 NaN 8.0 100% NaN Alex Murphy,Chris Walley,Hilary Rose,Dominic M... Comedy United Kingdom,Ireland English NaN 30.0 tv series 3.0 1 0 0 0 1
In [6]:
# profile = ProfileReport(df_tvshows)
# profile
In [7]:
def data_investigate(df):
    print('No of Rows : ', df.shape[0])
    print('No of Coloums : ', df.shape[1])
    print('**'*25)
    print('Colums Names : \n', df.columns)
    print('**'*25)
    print('Datatype of Columns : \n', df.dtypes)
    print('**'*25)
    print('Missing Values : ')
    c = df.isnull().sum()
    c = c[c > 0]
    print(c)
    print('**'*25)
    print('Missing vaules %age wise :\n')
    print((100*(df.isnull().sum()/len(df.index))))
    print('**'*25)
    print('Pictorial Representation : ')
    plt.figure(figsize = (10, 10))
    sns.heatmap(df.isnull(), yticklabels = False, cbar = False)
    plt.show()
In [8]:
data_investigate(df_tvshows)
No of Rows :  5432
No of Coloums :  20
**************************************************
Colums Names : 
 Index(['ID', 'Title', 'Year', 'Age', 'IMDb', 'Rotten Tomatoes', 'Directors',
       'Cast', 'Genres', 'Country', 'Language', 'Plotline', 'Runtime', 'Kind',
       'Seasons', 'Netflix', 'Hulu', 'Prime Video', 'Disney+', 'Type'],
      dtype='object')
**************************************************
Datatype of Columns : 
 ID                   int64
Title               object
Year                 int64
Age                 object
IMDb               float64
Rotten Tomatoes     object
Directors           object
Cast                object
Genres              object
Country             object
Language            object
Plotline            object
Runtime            float64
Kind                object
Seasons            float64
Netflix              int64
Hulu                 int64
Prime Video          int64
Disney+              int64
Type                 int64
dtype: object
**************************************************
Missing Values : 
Age                1954
IMDb                556
Rotten Tomatoes    4194
Directors          5158
Cast                486
Genres              323
Country             549
Language            638
Plotline           2493
Runtime            1410
Seasons             679
dtype: int64
**************************************************
Missing vaules %age wise :

ID                  0.000000
Title               0.000000
Year                0.000000
Age                35.972018
IMDb               10.235641
Rotten Tomatoes    77.209131
Directors          94.955817
Cast                8.946981
Genres              5.946244
Country            10.106775
Language           11.745214
Plotline           45.894698
Runtime            25.957290
Kind                0.000000
Seasons            12.500000
Netflix             0.000000
Hulu                0.000000
Prime Video         0.000000
Disney+             0.000000
Type                0.000000
dtype: float64
**************************************************
Pictorial Representation : 
In [9]:
# ID
# df_tvshows = df_tvshows.drop(['ID'], axis = 1)
 
# Age
df_tvshows.loc[df_tvshows['Age'].isnull() & df_tvshows['Disney+'] == 1, "Age"] = '13'
# df_tvshows.fillna({'Age' : 18}, inplace = True)
df_tvshows.fillna({'Age' : 'NR'}, inplace = True)
df_tvshows['Age'].replace({'all': '0'}, inplace = True)
df_tvshows['Age'].replace({'7+': '7'}, inplace = True)
df_tvshows['Age'].replace({'13+': '13'}, inplace = True)
df_tvshows['Age'].replace({'16+': '16'}, inplace = True)
df_tvshows['Age'].replace({'18+': '18'}, inplace = True)
# df_tvshows['Age'] = df_tvshows['Age'].astype(int)
 
# IMDb
# df_tvshows.fillna({'IMDb' : df_tvshows['IMDb'].mean()}, inplace = True)
# df_tvshows.fillna({'IMDb' : df_tvshows['IMDb'].median()}, inplace = True)
df_tvshows.fillna({'IMDb' : "NA"}, inplace = True)
 
# Rotten Tomatoes
df_tvshows['Rotten Tomatoes'] = df_tvshows['Rotten Tomatoes'][df_tvshows['Rotten Tomatoes'].notnull()].str.replace('%', '').astype(int)
# df_tvshows['Rotten Tomatoes'] = df_tvshows['Rotten Tomatoes'][df_tvshows['Rotten Tomatoes'].notnull()].astype(int)
# df_tvshows.fillna({'Rotten Tomatoes' : df_tvshows['Rotten Tomatoes'].mean()}, inplace = True)
# df_tvshows.fillna({'Rotten Tomatoes' : df_tvshows['Rotten Tomatoes'].median()}, inplace = True)
# df_tvshows['Rotten Tomatoes'] = df_tvshows['Rotten Tomatoes'].astype(int)
df_tvshows.fillna({'Rotten Tomatoes' : "NA"}, inplace = True)
 
# Directors
# df_tvshows = df_tvshows.drop(['Directors'], axis = 1)
df_tvshows.fillna({'Directors' : "NA"}, inplace = True)
 
# Cast
df_tvshows.fillna({'Cast' : "NA"}, inplace = True)
 
# Genres
df_tvshows.fillna({'Genres': "NA"}, inplace = True)
 
# Country
df_tvshows.fillna({'Country': "NA"}, inplace = True)
 
# Language
df_tvshows.fillna({'Language': "NA"}, inplace = True)
 
# Plotline
df_tvshows.fillna({'Plotline': "NA"}, inplace = True)
 
# Runtime
# df_tvshows.fillna({'Runtime' : df_tvshows['Runtime'].mean()}, inplace = True)
# df_tvshows['Runtime'] = df_tvshows['Runtime'].astype(int)
df_tvshows.fillna({'Runtime' : "NA"}, inplace = True)
 
# Kind
# df_tvshows.fillna({'Kind': "NA"}, inplace = True)
 
# Type
# df_tvshows.fillna({'Type': "NA"}, inplace = True)
# df_tvshows = df_tvshows.drop(['Type'], axis = 1)
 
# Seasons
# df_tvshows.fillna({'Seasons': 1}, inplace = True)
df_tvshows.fillna({'Seasons': "NA"}, inplace = True)
# df_tvshows = df_tvshows.drop(['Seasons'], axis = 1)
# df_tvshows['Seasons'] = df_tvshows['Seasons'].astype(int)
# df_tvshows.fillna({'Seasons' : df_tvshows['Seasons'].mean()}, inplace = True)
# df_tvshows['Seasons'] = df_tvshows['Seasons'].astype(int)
 
# Service Provider
df_tvshows['Service Provider'] = df_tvshows.loc[:, ['Netflix', 'Prime Video', 'Disney+', 'Hulu']].idxmax(axis = 1)
# df_tvshows.drop(['Netflix','Prime Video','Disney+','Hulu'], axis = 1)

# Removing Duplicate and Missing Entries
df_tvshows.dropna(how = 'any', inplace = True)
df_tvshows.drop_duplicates(inplace = True)
In [10]:
data_investigate(df_tvshows)
No of Rows :  5432
No of Coloums :  21
**************************************************
Colums Names : 
 Index(['ID', 'Title', 'Year', 'Age', 'IMDb', 'Rotten Tomatoes', 'Directors',
       'Cast', 'Genres', 'Country', 'Language', 'Plotline', 'Runtime', 'Kind',
       'Seasons', 'Netflix', 'Hulu', 'Prime Video', 'Disney+', 'Type',
       'Service Provider'],
      dtype='object')
**************************************************
Datatype of Columns : 
 ID                   int64
Title               object
Year                 int64
Age                 object
IMDb                object
Rotten Tomatoes     object
Directors           object
Cast                object
Genres              object
Country             object
Language            object
Plotline            object
Runtime             object
Kind                object
Seasons             object
Netflix              int64
Hulu                 int64
Prime Video          int64
Disney+              int64
Type                 int64
Service Provider    object
dtype: object
**************************************************
Missing Values : 
Series([], dtype: int64)
**************************************************
Missing vaules %age wise :

ID                  0.0
Title               0.0
Year                0.0
Age                 0.0
IMDb                0.0
Rotten Tomatoes     0.0
Directors           0.0
Cast                0.0
Genres              0.0
Country             0.0
Language            0.0
Plotline            0.0
Runtime             0.0
Kind                0.0
Seasons             0.0
Netflix             0.0
Hulu                0.0
Prime Video         0.0
Disney+             0.0
Type                0.0
Service Provider    0.0
dtype: float64
**************************************************
Pictorial Representation : 
In [11]:
df_tvshows.head()
Out[11]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country ... Plotline Runtime Kind Seasons Netflix Hulu Prime Video Disney+ Type Service Provider
0 1 Snowpiercer 2013 18 6.9 94 NA Daveed Diggs,Iddo Goldberg,Mickey Sumner,Aliso... Action,Drama,Sci-Fi,Thriller United States ... Set seven years after the world has become a f... 60 tv series 3 1 0 0 0 1 Netflix
1 2 Philadelphia 1993 13 8.8 80 NA Charlie Day,Glenn Howerton,Rob McElhenney,Kait... Comedy United States ... The gang, 5 raging alcoholic, narcissists run ... 22 tv series 18 1 0 0 0 1 Netflix
2 3 Roma 2018 18 8.7 93 NA Kevin McKidd,Ray Stevenson,Polly Walker,Kerry ... Action,Drama,History,Romance,War United Kingdom,United States ... In this British historical drama, the turbulen... 52 tv series 2 1 0 0 0 1 Netflix
3 4 Amy 2015 18 7 87 NA Amy Brenneman,Richard T. Jones,Jessica Tuck,Ma... Drama United States ... A family drama focused on three generations of... 60 tv series 6 1 0 1 1 1 Netflix
4 5 The Young Offenders 2016 NR 8 100 NA Alex Murphy,Chris Walley,Hilary Rose,Dominic M... Comedy United Kingdom,Ireland ... NA 30 tv series 3 1 0 0 0 1 Netflix

5 rows × 21 columns

In [12]:
df_tvshows.describe()
Out[12]:
ID Year Netflix Hulu Prime Video Disney+ Type
count 5432.000000 5432.000000 5432.000000 5432.000000 5432.000000 5432.000000 5432.0
mean 2716.500000 2010.668446 0.341311 0.293999 0.403351 0.033689 1.0
std 1568.227662 11.726176 0.474193 0.455633 0.490615 0.180445 0.0
min 1.000000 1901.000000 0.000000 0.000000 0.000000 0.000000 1.0
25% 1358.750000 2009.000000 0.000000 0.000000 0.000000 0.000000 1.0
50% 2716.500000 2014.000000 0.000000 0.000000 0.000000 0.000000 1.0
75% 4074.250000 2017.000000 1.000000 1.000000 1.000000 0.000000 1.0
max 5432.000000 2020.000000 1.000000 1.000000 1.000000 1.000000 1.0
In [13]:
df_tvshows.corr()
Out[13]:
ID Year Netflix Hulu Prime Video Disney+ Type
ID 1.000000 -0.031346 -0.646330 0.034293 0.441264 0.195409 NaN
Year -0.031346 1.000000 0.222316 -0.065807 -0.198675 -0.022741 NaN
Netflix -0.646330 0.222316 1.000000 -0.366515 -0.515086 -0.119344 NaN
Hulu 0.034293 -0.065807 -0.366515 1.000000 -0.377374 -0.075701 NaN
Prime Video 0.441264 -0.198675 -0.515086 -0.377374 1.000000 -0.151442 NaN
Disney+ 0.195409 -0.022741 -0.119344 -0.075701 -0.151442 1.000000 NaN
Type NaN NaN NaN NaN NaN NaN NaN
In [14]:
# df_tvshows.sort_values('Year', ascending = True)
# df_tvshows.sort_values('IMDb', ascending = False)
In [15]:
# df_tvshows.to_csv(path_or_buf= '/content/drive/MyDrive/Files/updated_otttvshows.csv', index = False)
 
# path = '/content/drive/MyDrive/Files/'
 
# udf_tvshows = pd.read_csv(path + 'updated_otttvshows.csv')
 
# udf_tvshows
In [16]:
# df_netflix_tvshows = df_tvshows.loc[(df_tvshows['Netflix'] > 0)]
# df_hulu_tvshows = df_tvshows.loc[(df_tvshows['Hulu'] > 0)]
# df_prime_video_tvshows = df_tvshows.loc[(df_tvshows['Prime Video'] > 0)]
# df_disney_tvshows = df_tvshows.loc[(df_tvshows['Disney+'] > 0)]
In [17]:
df_netflix_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 1) & (df_tvshows['Hulu'] == 0) & (df_tvshows['Prime Video'] == 0 ) & (df_tvshows['Disney+'] == 0)]
df_hulu_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 0) & (df_tvshows['Hulu'] == 1) & (df_tvshows['Prime Video'] == 0 ) & (df_tvshows['Disney+'] == 0)]
df_prime_video_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 0) & (df_tvshows['Hulu'] == 0) & (df_tvshows['Prime Video'] == 1 ) & (df_tvshows['Disney+'] == 0)]
df_disney_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 0) & (df_tvshows['Hulu'] == 0) & (df_tvshows['Prime Video'] == 0 ) & (df_tvshows['Disney+'] == 1)]
In [18]:
df_tvshows_age = df_tvshows.copy()
In [19]:
df_tvshows_age.drop(df_tvshows_age.loc[df_tvshows_age['Age'] == "NA"].index, inplace = True)
df_tvshows_age.drop(df_tvshows_age.loc[df_tvshows_age['Age'] == "NR"].index, inplace = True)
# df_tvshows_age = df_tvshows_age[df_tvshows_age.Age != "NA"]
df_tvshows_age['Age'] = df_tvshows_age['Age'].astype(int)
In [20]:
# Creating distinct dataframes only with the tvshows present on individual streaming platforms
netflix_age_tvshows = df_tvshows_age.loc[df_tvshows_age['Netflix'] == 1]
hulu_age_tvshows = df_tvshows_age.loc[df_tvshows_age['Hulu'] == 1]
prime_video_age_tvshows = df_tvshows_age.loc[df_tvshows_age['Prime Video'] == 1]
disney_age_tvshows = df_tvshows_age.loc[df_tvshows_age['Disney+'] == 1]
In [21]:
df_tvshows_age_group = df_tvshows_age.copy()
In [22]:
plt.figure(figsize = (10, 10))
corr = df_tvshows_age.corr()
# Plot figsize
fig, ax = plt.subplots(figsize=(10, 8))
# Generate Heat Map, allow annotations and place floats in map
sns.heatmap(corr, cmap = 'magma', annot = True, fmt = ".2f")
# Apply xticks
plt.xticks(range(len(corr.columns)), corr.columns);
# Apply yticks
plt.yticks(range(len(corr.columns)), corr.columns)
# show plot
plt.show()
fig.show()
<Figure size 720x720 with 0 Axes>
In [23]:
df_age_all_tvshows = df_tvshows_age

print('\nTV Shows with Age Rating are : \n')
df_age_all_tvshows.head(5)
TV Shows with Age Rating are : 

Out[23]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country ... Plotline Runtime Kind Seasons Netflix Hulu Prime Video Disney+ Type Service Provider
0 1 Snowpiercer 2013 18 6.9 94 NA Daveed Diggs,Iddo Goldberg,Mickey Sumner,Aliso... Action,Drama,Sci-Fi,Thriller United States ... Set seven years after the world has become a f... 60 tv series 3 1 0 0 0 1 Netflix
1 2 Philadelphia 1993 13 8.8 80 NA Charlie Day,Glenn Howerton,Rob McElhenney,Kait... Comedy United States ... The gang, 5 raging alcoholic, narcissists run ... 22 tv series 18 1 0 0 0 1 Netflix
2 3 Roma 2018 18 8.7 93 NA Kevin McKidd,Ray Stevenson,Polly Walker,Kerry ... Action,Drama,History,Romance,War United Kingdom,United States ... In this British historical drama, the turbulen... 52 tv series 2 1 0 0 0 1 Netflix
3 4 Amy 2015 18 7 87 NA Amy Brenneman,Richard T. Jones,Jessica Tuck,Ma... Drama United States ... A family drama focused on three generations of... 60 tv series 6 1 0 1 1 1 Netflix
8 9 Quincy 2018 18 7.3 82 NA Jack Klugman,John S. Ragin,Robert Ito,Joseph R... Crime,Drama,Mystery,Thriller United States ... Quincy and Sam are working as Coroners. Inspec... 60 tv series 8 1 0 0 0 1 Netflix

5 rows × 21 columns

In [24]:
df_age_0_tvshows = df_tvshows_age.loc[df_tvshows_age['Age'] == 0]

print('\nTV Shows with All Age Rating are : \n')
df_age_0_tvshows.head(5)
TV Shows with All Age Rating are : 

Out[24]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country ... Plotline Runtime Kind Seasons Netflix Hulu Prime Video Disney+ Type Service Provider
24 25 Kung Fu Panda Holiday 2010 0 6.8 NA Tim Johnson Jack Black,Dustin Hoffman,Angelina Jolie,Seth ... Animation,Short,Action,Comedy,Family United States ... The Winter Festival is coming and Po is asked ... 21 tv series NA 1 0 0 0 1 Netflix
29 30 Zapped 2014 0 6.8 6 Peter DeLuise James Buckley,Kenneth Collard,Louis Emerick,Pa... Comedy,Fantasy United Kingdom ... NA 30 tv series 3 1 1 0 1 1 Netflix
62 63 True: Happy Hearts Day 2019 0 8.3 NA Harold Harris Michela Luci,Jamie Watson,Eric Peterson,Anna C... Animation,Short,Adventure,Family,Fantasy NA ... NA NA tv series NA 1 0 0 0 1 Netflix
81 82 Beat Bugs: All Together Now 2017 0 7 NA Josh Wakely,Pablo De La Torre Ashleigh Ball,Lili Beaudoin,Shannon Chan-Kent,... Animation,Short,Adventure,Comedy,Family,Fantas... United States ... NA NA tv series NA 1 0 0 0 1 Netflix
103 104 Amazing Grace 2018 0 7.1 67 Michael Apted Kate Jenkinson,Sigrid Thornton,Alex Dimitriade... Drama Australia ... The series centres on midwife Grace and her pa... 118 tv series 1 0 1 0 0 1 Hulu

5 rows × 21 columns

In [25]:
df_age_7_tvshows = df_tvshows_age.loc[df_tvshows_age['Age'] == 7]

print('\nTV Shows with 7+ Age Rating are : \n')
df_age_7_tvshows.head(5)
TV Shows with 7+ Age Rating are : 

Out[25]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country ... Plotline Runtime Kind Seasons Netflix Hulu Prime Video Disney+ Type Service Provider
27 28 The Adventures of Sharkboy and Lavagirl 2005 7 8 19 Doug Walker Doug Walker,Malcolm Ray,Tamara Chambers,Barney... Comedy,Talk-Show NA ... If you thought the Spy Kids sequels were bad..... 29 tv series NA 1 0 0 0 1 Netflix
45 46 LEGO Jurassic World: The Indominus Escape 2016 7 5.7 NA NA A.J. LoCascio,Sendhil Ramamurthy,Fred Tatascio... Animation,Action,Adventure,Comedy,Family,Sci-Fi United States ... Jurassic park founder, Simon Masrani, recruits... 24 tv series 1 1 0 0 0 1 Netflix
76 77 Pac’s Scary Halloween 2016 7 5.4 NA NA Ashleigh Ball,Gabriel C. Brown,Ian James Corle... Animation,Action,Comedy,Drama,Family,Fantasy,S... United States ... NA 44 tv series NA 1 0 0 0 1 Netflix
88 89 EMI 2008 7 4.3 NA NA Carmindy,Ted Gibson,Clinton Kelly,Stacy London Family,Reality-TV NA ... NA 44 tv series NA 1 0 0 0 1 Netflix
99 100 Jake's Buccaneer Blast 2014 7 5.2 NA NA Megan Richie,Jadon Sand,Riley Thomas Stewart,D... Animation United States ... NA NA tv series 1 1 0 0 0 1 Netflix

5 rows × 21 columns

In [26]:
df_age_13_tvshows = df_tvshows_age.loc[df_tvshows_age['Age'] == 13]

print('\nTV Shows with 13+ Age Rating are : \n')
df_age_13_tvshows.head(5)
TV Shows with 13+ Age Rating are : 

Out[26]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country ... Plotline Runtime Kind Seasons Netflix Hulu Prime Video Disney+ Type Service Provider
1 2 Philadelphia 1993 13 8.8 80 NA Charlie Day,Glenn Howerton,Rob McElhenney,Kait... Comedy United States ... The gang, 5 raging alcoholic, narcissists run ... 22 tv series 18 1 0 0 0 1 Netflix
30 31 Yol Arkadaşım 2 2018 13 6.4 NA NA Bigkem Melisa Özelçi,Asena Keskinci,Serhat Mus... Drama,Romance Turkey ... NA NA tv series 2 1 0 0 0 1 Netflix
55 56 The Road to El Camino: Behind the Scenes of El... 2019 13 7.1 NA NA Charles Baker,Jonathan Banks,Melissa Bernstein... Documentary,Short United States ... NA 13 tv series NA 1 0 0 0 1 Netflix
82 83 The Birth Reborn 3 2018 13 NA NA NA Michel Odent Documentary NA ... NA NA tv series NA 1 0 0 0 1 Netflix
102 103 Get Smart 2008 13 8.2 51 Peter Segal Don Adams,Barbara Feldon,Edward Platt,Robert K... Action,Adventure,Comedy,Crime,Family,Mystery,S... United States ... Maxwell Smart is a bumbling secret agent, assi... 25 tv series 5 0 1 0 0 1 Hulu

5 rows × 21 columns

In [27]:
df_age_16_tvshows = df_tvshows_age.loc[df_tvshows_age['Age'] == 16]

print('\nTV Shows with 16+ Age Rating are : \n')
df_age_16_tvshows.head(5)
TV Shows with 16+ Age Rating are : 

Out[27]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country ... Plotline Runtime Kind Seasons Netflix Hulu Prime Video Disney+ Type Service Provider
54 55 My True Friend 2012 16 7.7 NA Atsajun Sattakovit Angelababy,Allen Deng,Yilong Zhu,Kai Tan,Anlia... Drama,Romance China ... A story that revolves around real estate agent... 103 tv series 1 1 0 1 0 1 Netflix
147 148 Dark Money 2018 16 6.6 96 NA Babou Ceesay,Jill Halfpenny,Susan Wokoma,Olive... Crime,Drama,Thriller United Kingdom ... Life is not always like the movies. Love isn't... 220 tv series 1 0 0 1 0 1 Prime Video
157 158 Halo 4: Forward Unto Dawn 2012 16 6.9 NA NA Thom Green,Anna Popplewell,Enisha Brewster,Aye... Action,Adventure,Family,Sci-Fi,Thriller,War United States ... In real life, Robert Oppenheimer was the scien... 100 tv series 1 0 0 1 0 1 Prime Video
161 162 Innocent 2011 16 5.4 64 NA Mario Casas,Juana Acosta,Josean Bengoetxea,Oli... Crime,Drama,Mystery,Thriller Spain ... Legendary poet, singer/songwriter and alleged ... 45 tv series 1 0 0 1 0 1 Prime Video
178 179 Houdini 2014 16 7.4 NA NA Adrien Brody,Kristen Connolly,Evan Jones,Tim P... Biography,Drama United States,Canada ... At the beginning of a nightly Alcoholics Anony... 174 tv series 1 0 0 1 0 1 Prime Video

5 rows × 21 columns

In [28]:
df_age_18_tvshows = df_tvshows_age.loc[df_tvshows_age['Age'] == 18]

print('\nTV Shows with 18+ Age Rating are : \n')
df_age_18_tvshows.head(5)
TV Shows with 18+ Age Rating are : 

Out[28]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country ... Plotline Runtime Kind Seasons Netflix Hulu Prime Video Disney+ Type Service Provider
0 1 Snowpiercer 2013 18 6.9 94 NA Daveed Diggs,Iddo Goldberg,Mickey Sumner,Aliso... Action,Drama,Sci-Fi,Thriller United States ... Set seven years after the world has become a f... 60 tv series 3 1 0 0 0 1 Netflix
2 3 Roma 2018 18 8.7 93 NA Kevin McKidd,Ray Stevenson,Polly Walker,Kerry ... Action,Drama,History,Romance,War United Kingdom,United States ... In this British historical drama, the turbulen... 52 tv series 2 1 0 0 0 1 Netflix
3 4 Amy 2015 18 7 87 NA Amy Brenneman,Richard T. Jones,Jessica Tuck,Ma... Drama United States ... A family drama focused on three generations of... 60 tv series 6 1 0 1 1 1 Netflix
8 9 Quincy 2018 18 7.3 82 NA Jack Klugman,John S. Ragin,Robert Ito,Joseph R... Crime,Drama,Mystery,Thriller United States ... Quincy and Sam are working as Coroners. Inspec... 60 tv series 8 1 0 0 0 1 Netflix
11 12 Wakefield 2017 18 8.1 72 Robin Swicord Rudi Dharmalingam,Mandy McElhinney,Geraldine H... Mystery Australia ... NA 106 tv series 1 1 0 0 0 1 Netflix

5 rows × 21 columns

In [29]:
f, ax = plt.subplots(1, 2 , figsize = (20, 5))
sns.distplot(df_tvshows_age['Age'],bins = 20, kde = True, ax = ax[0])
sns.boxplot(df_tvshows_age['Age'], ax = ax[1])
plt.show()
In [30]:
# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Age s Per Platform')
 
# Plotting the information from each dataset into a histogram
sns.histplot(prime_video_age_tvshows['Age'][:100], color = 'lightblue', legend = True, kde = True)
sns.histplot(netflix_age_tvshows['Age'][:100], color = 'red', legend = True, kde = True)
sns.histplot(hulu_age_tvshows['Age'][:100], color = 'lightgreen', legend = True, kde = True)
sns.histplot(disney_age_tvshows['Age'][:100], color = 'darkblue', legend = True, kde = True) 
 
# Setting the legend
plt.legend(['Prime Video', 'Netflix', 'Hulu', 'Disney+'])
plt.show()
In [31]:
def round_val(data):
    if str(data) != 'nan':
        return round(data)
In [32]:
df_tvshows_age_group['Age Group'] = df_tvshows_age['Age'].apply(round_val)
 
age_values = df_tvshows_age_group['Age Group'].value_counts().sort_index(ascending = False).tolist()
age_index = df_tvshows_age_group['Age Group'].value_counts().sort_index(ascending = False).index
 
# age_values, age_index
In [33]:
age_group_count = df_tvshows_age_group.groupby('Age Group')['Title'].count()
age_group_tvshows = df_tvshows_age_group.groupby('Age Group')[['Netflix', 'Hulu', 'Prime Video', 'Disney+']].sum()
age_group_data_tvshows = pd.concat([age_group_count, age_group_tvshows], axis = 1).reset_index().rename(columns = {'Title' : 'TV Shows Count'})
age_group_data_tvshows = age_group_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)
In [34]:
# Age Group with TV Shows Counts - All Platforms Combined
age_group_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)
Out[34]:
Age Group TV Shows Count Netflix Hulu Prime Video Disney+
3 16 1018 350 521 236 7
1 7 958 334 372 306 72
4 18 946 497 233 253 1
0 0 521 147 150 207 73
2 13 64 4 9 26 30
In [35]:
age_group_data_tvshows.sort_values(by = 'Age Group', ascending = False)
Out[35]:
Age Group TV Shows Count Netflix Hulu Prime Video Disney+
4 18 946 497 233 253 1
3 16 1018 350 521 236 7
2 13 64 4 9 26 30
1 7 958 334 372 306 72
0 0 521 147 150 207 73
In [36]:
fig = px.bar(y = age_group_data_tvshows['TV Shows Count'],
             x = age_group_data_tvshows['Age Group'], 
             color = age_group_data_tvshows['Age Group'],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows Count', 'x' : 'Age : '},
             title  = 'TV Shows with Group Age : All Platforms')

fig.update_layout(plot_bgcolor = "white")
fig.show()
In [37]:
fig = px.pie(age_group_data_tvshows,
             names = age_group_data_tvshows['Age Group'],
             values = age_group_data_tvshows['TV Shows Count'],
             color = age_group_data_tvshows['TV Shows Count'],
             color_discrete_sequence = px.colors.sequential.Teal)

fig.update_traces(textinfo = 'percent+label',
                  title = 'TV Shows Count based on Age Group')
fig.show()
In [38]:
df_age_group_high_tvshows = age_group_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False).reset_index()
df_age_group_high_tvshows = df_age_group_high_tvshows.drop(['index'], axis = 1)
# filter = (age_group_data_tvshows['TV Shows Count'] ==  (age_group_data_tvshows['TV Shows Count'].max()))
# df_age_group_high_tvshows = age_group_data_tvshows[filter]
 
# highest_rated_tvshows = age_group_data_tvshows.loc[age_group_data_tvshows['TV Shows Count'].idxmax()]
 
# print('\nAge with Highest Ever TV Shows Count are : All Platforms Combined\n')
df_age_group_high_tvshows.head(5)
Out[38]:
Age Group TV Shows Count Netflix Hulu Prime Video Disney+
0 16 1018 350 521 236 7
1 7 958 334 372 306 72
2 18 946 497 233 253 1
3 0 521 147 150 207 73
4 13 64 4 9 26 30
In [39]:
df_age_group_low_tvshows = age_group_data_tvshows.sort_values(by = 'TV Shows Count', ascending = True).reset_index()
df_age_group_low_tvshows = df_age_group_low_tvshows.drop(['index'], axis = 1)
# filter = (age_group_data_tvshows['TV Shows Count'] = =  (age_group_data_tvshows['TV Shows Count'].min()))
# df_age_group_low_tvshows = age_group_data_tvshows[filter]
 
# print('\nAge with Lowest Ever TV Shows Count are : All Platforms Combined\n')
df_age_group_low_tvshows.head(5)
Out[39]:
Age Group TV Shows Count Netflix Hulu Prime Video Disney+
0 13 64 4 9 26 30
1 0 521 147 150 207 73
2 18 946 497 233 253 1
3 7 958 334 372 306 72
4 16 1018 350 521 236 7
In [40]:
print(f'''
      Total '{df_tvshows_age['Age'].count()}' Titles are available on All Platforms, out of which\n
      You Can Choose to see TV Shows from Total '{age_group_data_tvshows['Age Group'].unique().shape[0]}' Age Group, They were Like this, \n
 
      {age_group_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)['Age Group'].unique()} etc. \n
 
      The Age Group with Highest TV Shows Count have '{age_group_data_tvshows['TV Shows Count'].max()}' TV Shows Available is '{df_age_group_high_tvshows['Age Group'][0]}', &\n
      The Age Group with Lowest TV Shows Count have '{age_group_data_tvshows['TV Shows Count'].min()}' TV Shows Available is '{df_age_group_low_tvshows['Age Group'][0]}'
      ''')
      Total '3507' Titles are available on All Platforms, out of which

      You Can Choose to see TV Shows from Total '5' Age Group, They were Like this, 

 
      [16  7 18  0 13] etc. 

 
      The Age Group with Highest TV Shows Count have '1018' TV Shows Available is '16', &

      The Age Group with Lowest TV Shows Count have '64' TV Shows Available is '13'
      
In [41]:
netflix_age_group_tvshows = age_group_data_tvshows[age_group_data_tvshows['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_age_group_tvshows = netflix_age_group_tvshows.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)
 
netflix_age_group_high_tvshows = df_age_group_high_tvshows.sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_age_group_high_tvshows = netflix_age_group_high_tvshows.drop(['index'], axis = 1)
 
netflix_age_group_low_tvshows = df_age_group_high_tvshows.sort_values(by = 'Netflix', ascending = True).reset_index()
netflix_age_group_low_tvshows = netflix_age_group_low_tvshows.drop(['index'], axis = 1)
 
netflix_age_group_high_tvshows.head(5)
Out[41]:
Age Group TV Shows Count Netflix Hulu Prime Video Disney+
0 18 946 497 233 253 1
1 16 1018 350 521 236 7
2 7 958 334 372 306 72
3 0 521 147 150 207 73
4 13 64 4 9 26 30
In [42]:
hulu_age_group_tvshows = age_group_data_tvshows[age_group_data_tvshows['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_age_group_tvshows = hulu_age_group_tvshows.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)
 
hulu_age_group_high_tvshows = df_age_group_high_tvshows.sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_age_group_high_tvshows = hulu_age_group_high_tvshows.drop(['index'], axis = 1)
 
hulu_age_group_low_tvshows = df_age_group_high_tvshows.sort_values(by = 'Hulu', ascending = True).reset_index()
hulu_age_group_low_tvshows = hulu_age_group_low_tvshows.drop(['index'], axis = 1)
 
hulu_age_group_high_tvshows.head(5)
Out[42]:
Age Group TV Shows Count Netflix Hulu Prime Video Disney+
0 16 1018 350 521 236 7
1 7 958 334 372 306 72
2 18 946 497 233 253 1
3 0 521 147 150 207 73
4 13 64 4 9 26 30
In [43]:
prime_video_age_group_tvshows = age_group_data_tvshows[age_group_data_tvshows['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_age_group_tvshows = prime_video_age_group_tvshows.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'TV Shows Count'], axis = 1)
 
prime_video_age_group_high_tvshows = df_age_group_high_tvshows.sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_age_group_high_tvshows = prime_video_age_group_high_tvshows.drop(['index'], axis = 1)
 
prime_video_age_group_low_tvshows = df_age_group_high_tvshows.sort_values(by = 'Prime Video', ascending = True).reset_index()
prime_video_age_group_low_tvshows = prime_video_age_group_low_tvshows.drop(['index'], axis = 1)
 
prime_video_age_group_high_tvshows.head(5)
Out[43]:
Age Group TV Shows Count Netflix Hulu Prime Video Disney+
0 7 958 334 372 306 72
1 18 946 497 233 253 1
2 16 1018 350 521 236 7
3 0 521 147 150 207 73
4 13 64 4 9 26 30
In [44]:
disney_age_group_tvshows = age_group_data_tvshows[age_group_data_tvshows['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
disney_age_group_tvshows = disney_age_group_tvshows.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'TV Shows Count'], axis = 1)
 
disney_age_group_high_tvshows = df_age_group_high_tvshows.sort_values(by = 'Disney+', ascending = False).reset_index()
disney_age_group_high_tvshows = disney_age_group_high_tvshows.drop(['index'], axis = 1)
 
disney_age_group_low_tvshows = df_age_group_high_tvshows.sort_values(by = 'Disney+', ascending = True).reset_index()
disney_age_group_low_tvshows = disney_age_group_low_tvshows.drop(['index'], axis = 1)
 
disney_age_group_high_tvshows.head(5)
Out[44]:
Age Group TV Shows Count Netflix Hulu Prime Video Disney+
0 0 521 147 150 207 73
1 7 958 334 372 306 72
2 13 64 4 9 26 30
3 16 1018 350 521 236 7
4 18 946 497 233 253 1
In [45]:
print(f'''
      The Age Group with Highest TV Shows Count Ever Got is '{df_age_group_high_tvshows['Age Group'][0]}' : '{df_age_group_high_tvshows['TV Shows Count'].max()}'\n
      The Age Group with Lowest TV Shows Count Ever Got is '{df_age_group_low_tvshows['Age Group'][0]}' : '{df_age_group_low_tvshows['TV Shows Count'].min()}'\n
      
      The Age Group with Highest TV Shows Count on 'Netflix' is '{netflix_age_group_high_tvshows['Age Group'][0]}' : '{netflix_age_group_high_tvshows['Netflix'].max()}'\n
      The Age Group with Lowest TV Shows Count on 'Netflix' is '{netflix_age_group_low_tvshows['Age Group'][0]}' : '{netflix_age_group_low_tvshows['Netflix'].min()}'\n
      
      The Age Group with Highest TV Shows Count on 'Hulu' is '{hulu_age_group_high_tvshows['Age Group'][0]}' : '{hulu_age_group_high_tvshows['Hulu'].max()}'\n
      The Age Group with Lowest TV Shows Count on 'Hulu' is '{hulu_age_group_low_tvshows['Age Group'][0]}' : '{hulu_age_group_low_tvshows['Hulu'].min()}'\n
      
      The Age Group with Highest TV Shows Count on 'Prime Video' is '{prime_video_age_group_high_tvshows['Age Group'][0]}' : '{prime_video_age_group_high_tvshows['Prime Video'].max()}'\n
      The Age Group with Lowest TV Shows Count on 'Prime Video' is '{prime_video_age_group_low_tvshows['Age Group'][0]}' : '{prime_video_age_group_low_tvshows['Prime Video'].min()}'\n
      
      The Age Group with Highest TV Shows Count on 'Disney+' is '{disney_age_group_high_tvshows['Age Group'][0]}' : '{disney_age_group_high_tvshows['Disney+'].max()}'\n
      The Age Group with Lowest TV Shows Count on 'Disney+' is '{disney_age_group_low_tvshows['Age Group'][0]}' : '{disney_age_group_low_tvshows['Disney+'].min()}'\n 
      ''')
      The Age Group with Highest TV Shows Count Ever Got is '16' : '1018'

      The Age Group with Lowest TV Shows Count Ever Got is '13' : '64'

      
      The Age Group with Highest TV Shows Count on 'Netflix' is '18' : '497'

      The Age Group with Lowest TV Shows Count on 'Netflix' is '13' : '4'

      
      The Age Group with Highest TV Shows Count on 'Hulu' is '16' : '521'

      The Age Group with Lowest TV Shows Count on 'Hulu' is '13' : '9'

      
      The Age Group with Highest TV Shows Count on 'Prime Video' is '7' : '306'

      The Age Group with Lowest TV Shows Count on 'Prime Video' is '13' : '26'

      
      The Age Group with Highest TV Shows Count on 'Disney+' is '0' : '73'

      The Age Group with Lowest TV Shows Count on 'Disney+' is '18' : '1'
 
      
In [46]:
fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_a_ax1 = sns.barplot(x = netflix_age_group_tvshows['Age Group'], y = netflix_age_group_tvshows['Netflix'], palette = 'Reds_r', ax = axes[0, 0])
h_a_ax2 = sns.barplot(x = hulu_age_group_tvshows['Age Group'], y = hulu_age_group_tvshows['Hulu'], palette = 'Greens_r', ax = axes[0, 1])
p_a_ax3 = sns.barplot(x = prime_video_age_group_tvshows['Age Group'], y = prime_video_age_group_tvshows['Prime Video'], palette = 'Blues_r', ax = axes[1, 0])
d_a_ax4 = sns.barplot(x = disney_age_group_tvshows['Age Group'], y = disney_age_group_tvshows['Disney+'], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_a_ax1.title.set_text(labels[0])
h_a_ax2.title.set_text(labels[1])
p_a_ax3.title.set_text(labels[2])
d_a_ax4.title.set_text(labels[3])
 
plt.show()
In [47]:
plt.figure(figsize = (20, 5))
sns.lineplot(x = age_group_data_tvshows['Age Group'], y = age_group_data_tvshows['Netflix'], color = 'red')
sns.lineplot(x = age_group_data_tvshows['Age Group'], y = age_group_data_tvshows['Hulu'], color = 'lightgreen')
sns.lineplot(x = age_group_data_tvshows['Age Group'], y = age_group_data_tvshows['Prime Video'], color = 'lightblue')
sns.lineplot(x = age_group_data_tvshows['Age Group'], y = age_group_data_tvshows['Disney+'], color = 'darkblue')
plt.xlabel('Age Group', fontsize = 15)
plt.ylabel('TV Shows Count', fontsize = 15)
plt.show()
In [48]:
print(f'''
      Accross All Platforms Total Count of Age Group is '{age_group_data_tvshows['Age Group'].unique().shape[0]}'\n
      Total Count of Age Group on 'Netflix' is '{netflix_age_group_tvshows['Age Group'].unique().shape[0]}'\n
      Total Count of Age Group on 'Hulu' is '{hulu_age_group_tvshows['Age Group'].unique().shape[0]}'\n
      Total Count of Age Group on 'Prime Video' is '{prime_video_age_group_tvshows['Age Group'].unique().shape[0]}'\n
      Total Count of Age Group on 'Disney+' is '{disney_age_group_tvshows['Age Group'].unique().shape[0]}'\n 
      ''')
      Accross All Platforms Total Count of Age Group is '5'

      Total Count of Age Group on 'Netflix' is '5'

      Total Count of Age Group on 'Hulu' is '5'

      Total Count of Age Group on 'Prime Video' is '5'

      Total Count of Age Group on 'Disney+' is '5'
 
      
In [49]:
fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_a_ax1 = sns.lineplot(y = age_group_data_tvshows['Age Group'], x = age_group_data_tvshows['Netflix'], color = 'red', ax = axes[0, 0])
h_a_ax2 = sns.lineplot(y = age_group_data_tvshows['Age Group'], x = age_group_data_tvshows['Hulu'], color = 'lightgreen', ax = axes[0, 1])
p_a_ax3 = sns.lineplot(y = age_group_data_tvshows['Age Group'], x = age_group_data_tvshows['Prime Video'], color = 'lightblue', ax = axes[1, 0])
d_a_ax4 = sns.lineplot(y = age_group_data_tvshows['Age Group'], x = age_group_data_tvshows['Disney+'], color = 'darkblue', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_a_ax1.title.set_text(labels[0])
h_a_ax2.title.set_text(labels[1])
p_a_ax3.title.set_text(labels[2])
d_a_ax4.title.set_text(labels[3])

plt.show()
In [50]:
fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_a_ax1 = sns.barplot(x = age_group_data_tvshows['Age Group'], y = age_group_data_tvshows['Netflix'], palette = 'Reds_r', ax = axes[0, 0])
h_a_ax2 = sns.barplot(x = age_group_data_tvshows['Age Group'], y = age_group_data_tvshows['Hulu'], palette = 'Greens_r', ax = axes[0, 1])
p_a_ax3 = sns.barplot(x = age_group_data_tvshows['Age Group'], y = age_group_data_tvshows['Prime Video'], palette = 'Blues_r', ax = axes[1, 0])
d_a_ax4 = sns.barplot(x = age_group_data_tvshows['Age Group'], y = age_group_data_tvshows['Disney+'], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_a_ax1.title.set_text(labels[0])
h_a_ax2.title.set_text(labels[1])
p_a_ax3.title.set_text(labels[2])
d_a_ax4.title.set_text(labels[3])
 
plt.show()